Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16190
    Prev
    Next
    INDEX
    Explanations

    gibberish

    np_token-act-pair-logits · gemini-2.0-flash

    words and phrases that have to do with giving instructions or advice

    oai_token-act-pair · gemini-2.0-flash

    instructions, advice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jboss
    -0.43
    Mine
    -0.41
     Mine
    -0.38
    writeFile
    -0.38
     commissions
    -0.37
    MessageState
    -0.37
     mine
    -0.37
    FieldNumber
    -0.36
    MINE
    -0.36
    mine
    -0.36
    POSITIVE LOGITS
    UnusedPrivate
    0.86
     disambiguazione
    0.85
     autorytatywna
    0.83
    GEBURTSDATUM
    0.80
    SharedDtor
    0.78
     tartalomajánló
    0.78
     ISNI
    0.77
    Geplaatst
    0.74
    تقاوى
    0.73
    verifyException
    0.71
    Activations Density 2.025%

    No Known Activations